FedSCS-XGB -- Federated Server-centric surrogate XGBoost for continual health monitoring

2026-03-06

AI Summary

This study addresses the challenge of distributed human activity recognition (HAR) for wearable devices in spinal cord injury patients, where data fragmentation and privacy constraints hinder centralized model training. To overcome this, the authors propose a server-centric federated learning framework based on XGBoost that preserves the algorithm’s core architecture—including histogram-based splitting and dynamic tree ensemble optimization—while theoretically guaranteeing convergence to the performance of centralized training. Experimental results on real-world wearable HAR datasets demonstrate that the proposed method achieves accuracy within 1% of centralized XGBoost and significantly outperforms baseline approaches such as IBM PAX. The framework thus effectively balances high predictive performance with strict data privacy preservation, offering a practical solution for privacy-sensitive HAR applications in clinical settings.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Humans and AI: Human-in-the-loop Machine Learning
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing

Abstract

Wearable sensors with local data processing can detect health threats early, enhance documentation, and support personalized therapy. In the context of spinal cord injury (SCI), which involves risks such as pressure injuries and blood pressure instability, continuous monitoring can help mitigate these by enabling early deDtection and intervention. In this work, we present a novel distributed machine learning (DML) protocol for human activity recognition (HAR) from wearable sensor data based on gradient-boosted decision trees (XGBoost). The proposed architecture is inspired by Party-Adaptive XGBoost (PAX) while explicitly preserving key structural and optimization properties of standard XGBoost, including histogram-based split construction and tree-ensemble dynamics. First, we provide a theoretical analysis showing that, under appropriate data conditions and suitable hyperparameter selection, the proposed distributed protocol can converge to solutions equivalent to centralized XGBoost training. Second, the protocol is empirically evaluated on a representative wearable-sensor HAR dataset, reflecting the heterogeneity and data fragmentation typical of remote monitoring scenarios. Benchmarking against centralized XGBoost and IBM PAX demonstrates that the theoretical convergence properties are reflected in practice. The results indicate that the proposed approach can match centralized performance up to a gap under 1\% while retaining the structural advantages of XGBoost in distributed wearable-based HAR settings.

Problem

• federated learning
• human activity recognition
• wearable sensors
• data heterogeneity
• spinal cord injury

Innovation

• Federated Learning
• XGBoost
• Human Activity Recognition
• Wearable Sensors
• Distributed Machine Learning